The MaML Podcast - Medicine & Machine Learning

Dr. Nina Kottler is the associate chief medical officer of clinical artificial intelligence and vice president of clinical operations for Radiology Partners, the largest radiology practice in the US, serving over 3,250 hospitals and other healthcare facilities, interpreting over 53 million exams annually.  Host: David Wu Twitter: @davidjhwu Audio Producer: Aaron Schumacher LinkedIn: Aaron Schumacher  Video Editor + Art: Saurin Kantesaria Instagram: saorange314 00:00:58 What brought you to the intersection of medicine and artificial intelligence? 00:07:00 The importance of translating between clinicians and AI engineers 00:12:54 The origins of Radiology Partners  00:16:40 Dr. Kottler’s start in Teleradiology  00:21:18 The transition form analog to digital in Radiology  00:27:35 The current state of Radiology Partners 00:32:00 When did Dr. Kottler become a leader in the AI projects? 00:45:00 AI models that Radiology Partners use  00:52:00 Fragility, Technological Evaluation and Business evaluation in Radiology AI systems 00:56:10 Dr. Kottler’s thoughts on what the future of AI and Radiology will look like.  01:00:30 Dr. Kottler’s advice for people in medicine desiring unique paths.  01:02:45 What brings you joy?

Munjal Shah is the co-founder and CEO of Hippocratic AI, a new startup in Generative AI + Healthcare. Hippocratic is building a safety-focused large language model specifically built for the healthcare industry.  Host: David Wu Twitter: @davidjhwu Audio Producer: Aaron Schumacher LinkedIn: Aaron Schumacher  Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Time Stamps: 00:00:58 What brought you to the intersection of medicine and artificial intelligence? 00:06:20 Overview of the American Healthcare System  00:08:06 Hippocratic AI and the Adherence Problem within healthcare  00:14:30 Building an AI Chronic Care Nurse for specific conditions  00:17:15 AI systems and medical co-morbidities  00:24:00 The process of building Hippocratic AI 00:32:45 Becoming more efficient than ChatGPT4 00:33:48 Navigating the problem of hallucinations with Hippocratic AI 00:39:30 How close are we to Health General Intelligence (HGI)? 00:45:40 What advice would you give to someone interested in starting their own company? 00:48:20 How did mentorship shape your path? 00:49:40 What brings you joy? 00:52:25 How do you find novel ideas for start-ups?

Dr. Mamdani is a professor, pharmacist, and epidemiologist. He is the Vice President of Data Science and Advanced Analytics at Unity Health Toronto and Director of the University of Toronto Temerty Centre for Artificial Intelligence Research and Education in Medicine (T-CAIREM). Dr. Mamdani’s team bridges advanced analytics including machine learning with clinical and management decision making to improve patient outcomes and hospital efficiency. Dr. Mamdani is also Professor in the Temerty Faculty of Medicine, the Leslie Dan Faculty of Pharmacy, and the Institute of Health Policy, Management and Evaluation of the Dalla Lana School of Public Health at the University of Toronto. He is also a Faculty Affiliate of the Vector Institute. He has published over 500 studies in peer-reviewed journals. Host: Raeesa Kabir  Audio Producer: Melanie Bussan Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Social Media: Nikhil Kapur Time Stamps: 0:00 Dr. Mamdani’s Background and Career Path 9:30 Where current data driven medicine strategies fall short and how AI can step in 17:00 How Dr. Mamdani’s work in AI and machine learning began 22:00 Applied Health Research Center and the Ontario Policy Research Network 28:45 The impact of utilizing machine learning and AI at the level of patient care - Chart Watch 35:50 Logistics of Developing and Implementing AI solutions 39:10 Insights Gained - From Purpose to Implementation 43:30 Directing Multiple Projects - Recruitment of AI Team  47:45 Future Projects: Back to AI Basics  54:15 Future of AI in Medicine - Fostering trust in AI 57:20 Advice to Younger Self

CardinalKit (now Spezi) is an open-source framework for Digital Health Applications and Research. They were recently featured in the news for releasing HealthGPT, an experimental iOS app that lets you query your health data. Spezi is housed in the Stanford Byers Center for Biodesign and directed by Oliver Aalami, MD with Vishnu Ravi, MD as lead architect. Also joining us on this interview is postdoc Paul Schmiedmayer, PhD. Spezi provides a suite of tools to build modern, interoperable digital health tools from the ground up, from the app itself to storing and analyzing collected data in the cloud. It is designed to accelerate rapid prototyping of digital health applications by reducing costs by as much as 75% (~$150,000) and timelines by 12 months. Host: David Wu Twitter: @davidjhwu  Audio Producer + Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Social Media: Nikhil Kapur Time Stamps: 00:58 - The expertise behind Spezi (CardinalKit) 08:03 - Healthcare has a lack of data standardization + Why you should know about HL7 FHIR 14:13 - How did Spezi (CardinalKit) become what it is today? 18:26 - Drink Spezi! 19:53 - Making code/healthcare data more modular and user-friendly 26:40 - Translating a med student's sensor research to a useable device for kids with cerebral palsy 31:20 - From a $40,000 eczema patch test in clinic to a completely at-home test 35:45 - Using healthGPT to make health data easy to understand for patients (LLM on FHIR) 42:35 - How do you deal with privacy issues? 49:33 - What do you think the future of AI in medicine will look like in 10-20 years? 52:00 - Applications where using only an LLM doesn't always work (a case for hybrid systems) 55:30 - What brings you joy? 58:43 - What makes a successful digital health team?

Dereck Paul, MD is a cofounder and the CEO of Glass Health, an AI-powered medical knowledge management and clinical decision-making platform that helps clinicians provide better patient care. Previously, he was an internal medicine resident at Brigham and Women's Hospital, Harvard Medical School and a medical student at the UCSF School of Medicine. Host: David Wu Twitter: @davidjhwu  Audio Producer + Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Social Media: Nikhil Kapur Time Stamps: 01:13 - From music major to med school to making a startup 06:30 - Poor healthcare technology = physician burnout, the motivation for building Glass Health 09:15 - Glass Notebook - "Notion for doctors" 11:24 - Building a startup in the era of Chat-GPT 13:50 - What doctors need in an AI-assisted diagnosis software 19:15 - Transition towards a more AI oriented technology - Glass AI 23:00 - How does Glass AI make accurate diagnoses? 28:40 - Why doctors need to be involved in building clinical AI products 30:50 - Practical usage of Glass AI in the clinic 33:04 - Why Glass AI will be more trustworthy than Chat-GPT in writing clinical notes 37:43 - Why LLMs don't need to be perfect for use in the clinic 40:28 - Ethical implications of Glass AI and similar products 45:34 - Should we disclose when we use AI to write a clinical note? 49:13 - What do you think the future of AI in medicine will look like in 10-20 years? 52:30 - What brings you joy? What gives your life meaning? 56:10 - Would you ever go back to being a musician?

Jerry Liu is the co-founder and creator of LlamaIndex (formerly known as GPT-Index), an interface that allows users to connect their data to LLM’s such as Chat-GPT. He has a B.S. in Computer Science from Princeton and has worked at companies such as Quora, Uber, and Robust Intelligence prior to starting LlamaIndex. Host: David Wu Twitter: @davidjhwu Audio Producer: Aaron Schumacher LinkedIn: Aaron Schumacher  Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Social Media: Nikhil Kapur Time Stamps: 01:25 The path to starting LlamaIndex + initial ideas 07:09 LLMs like Chat-GPT vs traditional machine learning 10:00 4 steps of traditional machine learning 10:45 How do large LLMs change the game? 14:11 How does LlamaIndex help LLMs work with unstructured data? 18:08 How do you work with gigabytes of private data? 19:57 Organizing words and paragraphs by topic with embeddings 24:55 The importance of structuring data 26:00 3 key abstractions in LlamaIndex 29:25 Medical use cases for LlamaIndex 31:29 Increasing efficiency in medicine 33:25 An AI medical Research Assistant (Insight) 34:31 Other methods of connecting LLMs to data 36:55 What is langchain? 39:56 What work in the AI and LLM space excites you the most? 42:23 Do you ever feel scared about the developments of AI? 43:45 Llamas and Machine Learning 45:36 What do you think the future of AI in medicine will look like in 10-20 years? 47:24 What advice would you give to grad students, med students, and other early career professionals getting into AI and medicine?

Dr. Ryan earned both a doctorate of medicine (M.D.) and master in public health (M.P.H.) degree from the University of Connecticut in 2001. He completed his postdoctoral training at Harvard's Beth Israel Deaconess Medical Center in Boston, including a chief residency and cardiology fellowship. In 2014 Dr. Ryan started Boards and Beyond, an online lecture library used by medical students across the world to prepare for board exams. In 2022, Dr. Ryan sold his company to McGraw Hill and will continue working to build medical education materials.  Host: David Wu Twitter: @davidjhwu Audio Producer: Aaron Schumacher LinkedIn: Aaron Schumacher  Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Social Media: Nikhil Kapur Time Stamps: 00:55 - How did you come to create Boards and Beyond  08:00 - What was it like to make videos outside of your specialty 09:30 - The launch of Boards and Beyond  12:22 - Designing the Curriculum for Boards and Beyond  15:10 - Jason Ryan on selling Boards and Beyond to McGraw Hill  16:58 - What is next for Jason Ryan? 18:00 - Who were Jason Ryan’s favorite teachers  19:48 - What makes a good teacher  23:40 - What are your thoughts on the future of artificial intelligence and medical education 30:03 - Thoughts on Khan Academy’s AI-based Khanmigo  31:25 - Jason Ryan’s thoughts on becoming a clinician  35:29 - Mentorship throughout Jason Ryan’s career  37:35 - Could medical training be shortened? 41:40 - What do you think the future of medicine and artificial intelligence will look like? 43:10 - What advice would you give medical students today? 46:14 - What brings you joy and meaning? What are your greatest fears? 52:48 - What was your lowest point in medical training and how did you overcome it?

Mushtaq Bilal is a postdoctoral researcher at the University of Southern Denmark. He earned his PhD in comparative literature from Binghamton University. He works on simplifying the process of academic writing and writes about ethical use of artificial intelligence for academic purposes. Host: Raeesa Kabir Audio Producer: Melanie Bussan Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Social Media: Nikhil Kapur Music: Caligula - Windows96. Used with Artist's Permission. Introduction and Mushtaq’s path: 0:00 seconds  Overview on using AI tools for efficient writing: 8:00 seconds Keeping up to date with all the new apps: 18:00 seconds  Leveling the playing field of academia: 23:15 seconds  Ethical considerations of AI powered writing tool: 40:30 seconds Mushtaq’s tutorial for simplifying the academic writing process: 53:20 seconds Fun ending question and ending: 57:30

John Kang, MD, Ph.D. is an assistant professor of Radiation Oncology and Biomedical Informatics Lead at the University of Washington in Seattle. His research interests include the application of Natural Language Processing (NLP) to examine trends in the MaML space. He is a physician-data scientist passionate about uncovering the complex interactions underneath large datasets. He has over 10 years of experience in the novel applications of computational modeling and machine learning in biology systems.  Host: David Wu Twitter: @davidjhwu Audio Producer: Aaron Schumacher Twitter: a_schu95 Video Editor + Art: Saurin Kantesaria Instagram: saorange314 Social Media: Nikhil Kapur 00:45 Could you tell us about your journey to the intersection of medicine and machine learning 07:40 Balancing Residency Training and staying caught up on research in the machine learning space 16:00 Using machine learning to understand biostatistics  18:12 How would you describe the research that you find the most exciting / Unsupervised learning  23:00 Overview of Word Embedding and addressing  potential bias  29:25 Dr. Kang’s application of word embedding for research funding  42:52 The intersection of artificial intelligence and human intelligence  45:35 T-SNE / T-Distributed Stochastic Neighbor Embedding in grant analysis  50:50 Has T-SNE helped guide Dr. Kang’s research and grant writing  57:00 The future of creativity and ChatGPT  01:02:30 Fear vs Hope in the Medicine and Machine Learning space  01:07:00 What do you think is the future of the MaML space in the next 10-20 years? 01:11:02 What advice would you give yourself as you were finishing medical school?

Welcome back to the third season of the medicine and machine learning podcast! We are kicking off our year with a very unique episode. Our "guest" is ChatGPT! ChatGPT is an artificial-intelligence chatbot developed by OpenAI and launched in November 2022. Since its launch, ChatGPT has been an internet and media sensation. Usage is currently freely available to the public because ChatGPT is in its research and feedback-collection phase. This open interface has been hugely influential in bringing public attention to how AI can be used as a multidisciplinary resource. In this episode, the MaML team asked some fun questions of ChatGPT and gave the answers a voice with text-to-speech software! Don’t forget to follow us on twitter @themamlpodcast! contact@themamlpodcast.com Host and Producer: Madeline Ahern / Twitter @maddie_ahern Host: David Wu / Twitter: @davidjhwu Host: Raeesa Kabir Artwork: Saurin Kantesaria Music: Caligula - Windows96. Used with Artist's Permission. 00:40 GPT-4's Intro 01:40 The "Path" of ChatGPT 03:20 ChatGPT's advice for passing STEP exams 07:25 GPT-4 Tackles an Ethics Question 12:00 GPT-4 Tackles a STEP 1 Practice Question 14:44 GPT-4 Tackles a Clinical Scenario 19:02 ChatGPT has passed the boards, how would it do on CASPer? 20:15 The future of AI in medicine 27:31 Closing Remarks

Dr Matthew Lungren is the Chief Medical Information Officer at Nuance Communications, a Microsoft Company. As a physician and clinical machine learning researcher, he maintains a part-time interventional radiology practice at UCSF while also serving as adjunct faculty for other leading academic medical centers including Stanford and Duke. Prior to joining Microsoft, Dr Lungren led the Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI). This interview offers great insight for anyone who is interested in non-traditional career paths in medicine at the cutting edge of the MaML space. I hope you all enjoy! and don’t forget to follow us on twitter @themamlpodcast! contact@themamlpodcast.com Host: David Wu / Twitter: @davidjhwu Producer: Aaron Schumacher / Twitter: @a_schu95 Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96. Used with Artist's Permission. 00:40 Could you tell us about your path coming to the intersection of medicine and artificial intelligence? 07:00 What literature are you a fan of? 08:50 Where will the next great American Author come from? 14:00 Tell us about your work with Nuance. 17:50 Could you tell us the background of Nuance and Dragon Dictation? 19:55 Tell us about Nuance products that are offered. 23:45 How much code should future physicians know? 28:30 What is a typical day like as chief medical officer 31:30 Do you have any advice for medical students interested in nontraditional career paths? 34:30 How do you balance clinical practice and industry work? 40:40 What are you excited about most in the next 10-20 years? 44:15 How has mentorship shaped your path? 46:08 What advice would you give yourself at your medical school graduation?

Dr. Kaz Nelson is a Fellow of the American Board of Psychiatry and Neurology and serves as Associate Professor in the Department of Psychiatry and Behavioral Sciences and the Associate Designated Institutional Official in the Office of Graduate Medical Education at the University of Minnesota Medical School. She is also host of “The Mind Deconstructed.” In this podcast, Nelson and her brother George dispel myths, address listener questions, and inform the public about mental health and a life worth living. Connect with Dr. Nelson on the following platforms: Twitter: @kazjnelson Facebook: @kazjnelson Youtube: The Mind Deconstructed Host: Madeline Ahern @maddie_ahern Producer: Kirsi Oldenburg Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96, Used with artist permission 01:13 Introduction - Dr. Kaz Nelson 06:20 Sacrifices of Physicians (and their families) 08:25 Limitations of the Mental Health System 13:00 AI Chatbots: Helpful or Harmful? 23:00 High-Acuity Care and Psychiatric Crises 30:30 First Interactions with the Mental Health System 37:10 The Mind Deconstructed 43:45 The Future of AI, Chat GPT 47:30 The Pull of the Status Quo 53:24 Advice to our Listeners

Dr. John Sargent: Dr. John Sargent is the co-founder of BroadReach Group and an internationally recognized thought leader who brings extensive experience in health systems strengthening large-scale patient education programs and the creation and implementation of public-private partnerships in emerging markets. Prior to co-founding BroadReach Group, he obtained his Doctor of Medicine from Harvard Medical School and gained experience as a strategic and operational consultant with expertise spanning multiple disease areas across public and private health sectors. Annika Krugel: Annika Krugel is the Client Director for Vantage Health Technologies, which is a platform from BroadReach that uses AI to aggregate all data in an area or a clinic and then give individualized decision support, operational tools, and step-by-step workflows to empower healthcare workers. Annika has a Master’s Degree in Development Studies and has 15 years of experience across civil society and the public- and private sectors in various roles but always in a coordinating capacity. 1:15- Journey to the intersection of medicine and 9:00- Foundation of the BroadReach Group and current work 23:00- Inception of Vantage Health Technologies 25:20- Vantage Health Technologies’ role in the pandemic response 35:30- BroadReach Group and Vantage Health Technologies’ overall work across the globe 37:00- Future work 45:00- Future of big data and AI in medicine 50:30- Ensuring patient data privacy and security 52:30- Advice and ending thoughts

Dr. Joe Zhang is an Intensive Care doc and health data scientist. He holds a Wellcome Trust fellowship in health informatics and artificial intelligence (AI) at Imperial College London. He has extensive experience in developing and deploying informatics and data solutions in the NHS, and is currently working at the intersection of data science, policy, and infrastructure. contact@themamlpodcast.com Host: David Wu / Twitter: @davidjhwu Producer: Aaron Schumacher / Twitter: @a_schu95 Artwork & Video: Saurin Kantesaria Music: Caligula - Windows96. Used with Artist Permission. 1:10 Your path to the intersection of Medicine and Machine Learning 4:45 What Electronic health records are used in the UK and how does the NHS operate? 12:40 Who uses the data you gather in the NHS? 12:40 Could you tell us about your new publication on the vertical translation of data in AI? 28:00 Can you speak to regulatory bodies and the implementation of AI into healthcare? 32:00 The global clinical AI dashboard 37:25 Any future projects in the pipeline? 39:00 What projects tend to have the most success at being integrated into healthcare? 41:08 How has mentorship shaped your path? 42:15 What do you think the future of AI in medicine will look like in 10 to 20 years? 46:50 What brings you joy and meaning? 48:00 Closing thoughts for the listeners

Beth Beadle, MD, PhD is the Director of Head & Neck Radiation Oncology at Stanford and co-creator of the Radiation Planning Assistant, a fully automated treatment planning assistant.  00:56 How did you come to the intersection of medicine and AI? 03:20  What is radiation oncology and why does it fit well with AI? 05:54 How has radiation changed in your lifetime? 09:19 What is the Radiation Planning Assistant? 13:10 Describe radiation oncology workflow before the use of the radiation planning assistant 20:45  How does the model compare humans? 23:45 Where was the data source for the radiation Planning Assistant Model? 26:45 What safeguards exist for RPA? 28:00 What has been the response from other physicians, physicists, and patients to this model? 33:30 Timeline for implementation of the radiation planning assistant? 34:45 Background of the Radiation Planning Assistant 38:25 Future of Radiation Planning Assistant implementation 40:55 Adaptive planning in radiation oncology 43:15 Future of the Radiation Planning Assistant in the next 10 years 44:50 Are there any other projects being planned currently? 47:00 How has mentorship shaped your path? 50:25 What is the future of AI in medicine in 10-20 years 51:48 What advice would you tell yourself when you were graduating from medical school 53:20 What brings your life joy and meaning? 54:50 What are your greatest fears? 55:15 Favorite places to travel?